Predict protein-ligand docking poses and confidence scores from PDB structures or sequences.
npx skills add https://github.com/ovachiever/droid-tings --skill diffdock
Please help me install this Agent Skill. Skill: diffdock Source: https://github.com/ovachiever/droid-tings/tree/main/skills/diffdock Command: npx skills add https://github.com/ovachiever/droid-tings --skill diffdock
DiffDock predicts ligand-binding poses to protein targets using diffusion-based models, generating multiple candidate poses with confidence scores for structure-based drug design and virtual screening.
Example: run single-pose docking for a protein and SMILES ligand; output ranks and confidences.
High-intent search queries and answers about installing and using this skill.
Protein-ligand docking predicts how small molecules bind to protein targets. DiffDock uses diffusion-based models to generate multiple candidate poses with confidence scores, enabling structure-based drug design and virtual screening workflows from PDB structures or protein sequences and ligands supplied as SMILES, SDF, or MOL2 formats.
Yes. DiffDock supports protein sequences via ESMFold, which predicts 3D structures from amino acid sequences. This enables docking workflows when only sequence information is available, eliminating the need for experimentally resolved PDB files.
DiffDock accepts SMILES strings, SDF files, MOL2 files, and ligand descriptions. This format flexibility integrates seamlessly into diverse virtual screening pipelines and chemical databases without requiring manual conversion steps.
DiffDock supports batch docking to process multiple ligand-protein complexes in a single workflow. It outputs pose files in SDF format and confidence scores in a ranked text file, enabling high-throughput virtual screening and prioritization of candidate molecules.
DiffDock requires PyTorch, RDKit, ESM, NumPy, and TorchVision. GPU-accelerated execution is supported to reduce inference time for diffusion-model predictions, making large-scale screening feasible while CPU execution remains available for smaller datasets.
Yes. DiffDock supports integration with external scoring tools to augment or replace its built-in confidence scoring. This enables custom ranking strategies and compatibility with established computational chemistry pipelines.
felixboehmPredict protein-ligand binding poses and confidence scores with diffusion models.
ovachieverPredict protein-ligand docking poses and confidence scores from PDB structures or sequences.
AlterLab-IEUPredict protein-ligand binding poses and confidence scores via diffusion-model docking.
learningmatter-mitDock small-molecule ligands into a protein receptor using AutoDock Vina.
